© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 7710
    Prev
    Next
    INDEX
    Explanations

    terms related to various categories such as music, politics, crime, and different medical conditions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to crime, media, pop culture, and significant figures or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ingham
    -0.75
    ries
    -0.75
    hips
    -0.72
    nings
    -0.71
    ships
    -0.70
    icka
    -0.70
    rice
    -0.70
    liness
    -0.68
    older
    -0.68
    ls
    -0.67
    POSITIVE LOGITS
    ħĭ
    0.74
    ãĥŁ
    0.70
     metic
    0.63
    æ©
    0.59
    ãĥĻ
    0.58
    ãģı
    0.56
    ãĤ«
    0.53
     Juda
    0.52
    ĵĺ
    0.52
    éĹĺ
    0.52
    Activations Density 0.511%

    No Known Activations